BaKGraSTeC: A Background Knowledge Graph Based Method for Short Text Classification

Jiang, Xuhui; Shen, Yinghan; Wang, Yuanzhuo; Jin, Xiaolong; Cheng, Xueqi

doi:10.1109/icbk50248.2020.00058

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [1] took conceptual information as a kind of knowledge and incorporated it into deep neural networks. Jiang et al [28] used conceptualization information for short text classification. Xie et al [29] explained the relationship between entities by conceptualizing entity pairs.…”

Section: Conceptualizationmentioning

confidence: 99%

Concept-Based Label Distribution Learning for Text Classification

Li¹,

Huang²,

Li³

et al. 2022

Int J Comput Intell Syst

View full text Add to dashboard Cite

Text classification is a crucial task in data mining and artificial intelligence. In recent years, deep learning-based text classification methods have made great development. The deep learning methods supervise model training by representing a label as a one-hot vector. However, the one-hot label representation cannot adequately reflect the relation between an instance and the labels, as labels are often not completely independent, and the instance may be associated with multiple labels in practice. Simply representing the labels as one-hot vectors leads to overconfidence in the model, making it difficult to distinguish some label confusions. In this paper, we propose a simulated label distribution method based on concepts (SLDC) to tackle this problem. This method captures the overlap between the labels by computing the similarity between an instance and the labels and generates a new simulated label distribution for assisting model training. In particular, we incorporate conceptual information from the knowledge base into the representation of instances and labels to address the surface mismatching problem when instances and labels are compared for similarity. Moreover, to fully use the simulated label distribution and the original label vector, we set up a multi-loss function to supervise the training process. Expensive experiments demonstrate the effectiveness of SLDC on five complex text classification datasets. Further experiments also verify that SLDC is especially helpful for confused datasets.

show abstract

Section: Conceptualizationmentioning

confidence: 99%

Concept-Based Label Distribution Learning for Text Classification

Li¹,

Huang²,

Li³

et al. 2022

Int J Comput Intell Syst

View full text Add to dashboard Cite

show abstract

“…The triples in the knowledge graph (KG) contain the relationships between various entities, providing rich semantic background knowledge for various natural language processing (NLP) tasks, such as natural language representation [1], question answering [2], image captioning [3], and text classification [4]. Consequently, automatically constructing knowledge graphs directly from natural texts has attracted close attentions of re-searchers in recent years [5]- [7].…”

Section: Introductionmentioning

confidence: 99%

Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training

Cai¹,

Liao²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Modern supervised learning neural network models require a large amount of manually labeled data, which makes the construction of domain-specific knowledge graphs timeconsuming and labor-intensive. In parallel, although there has been much research on named entity recognition and relation extraction based on distantly supervised learning, constructing a domain-specific knowledge graph from large collections of textual data without manual annotations is still an urgent problem to be solved. In response, we propose an integrated framework for adapting and re-learning knowledge graphs from one coarse domain (biomedical) to a finer-define domain (oncology). In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation. Consequently, no manual data annotation is required to train the model. We introduce a novel iterative training strategy to facilitate the discovery of domainspecific named entities and triples. Experimental results indicate that the proposed framework can perform domain adaptation and construction of knowledge graph efficiently.

show abstract